Agent skill

Issue Workflow Guardrail

by kxn in kxn/codex-remote-feishu

A skill your agent uses when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots…

No licenceAuto-check passedAI & LLM Engineering

Install Issue Workflow Guardrail

skills CLI
$ npx skills add kxn/codex-remote-feishu --skill issue-workflow-guardrail -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kxn/codex-remote-feishu issue-workflow-guardrail --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kxn/codex-remote-feishu.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/issue-workflow-guardrail .claude/skills/issue-workflow-guardrail && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
issue-workflow-guardrail
GitHub stars
329
Token cost
~1.3k tokens
SKILL.md length
400 words
Files
3 (incl. scripts)
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

A skill your agent uses when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots…

  • Works in 4 steps: 单一执行面,预期一个 commit 能收尾 → 不碰状态机 / 迁移 / 安全 / 权限 / 协议 / 跨 surface 行为 → 有明确测试或验证路径 → …
  • Handling a GitHub issue in this repository: raw issue shaping
  • SKILL.md covers 定位, 模式选择, 入口 and fast 合同, plus 9 more sections
  • Runs Shell scripts from its folder; calls rg, bash and gh

What it does

Issue Workflow Guardrail is an agent skill from kxn/codex-remote-feishu. Use when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots on real handoffs, product decision gates, result roll-up, and close-out. Run the prepare/finish entry points and keep the issue body current.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml` and `scripts/issuectl.sh`).

It sits in AI & LLM Engineering. It works with GitHub. The repository describes itself as: Yet another codex remote in feishu.

When your agent uses it

  • Handling a GitHub issue in this repository: raw issue shaping
  • Implementability reassessment
  • Fast/full classification
  • Parent/child orchestration

Example prompts

  • “/issue-workflow-guardrail”

Requirements

  • A Bash shell

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 单一执行面,预期一个 commit 能收尾
  2. 不碰状态机 / 迁移 / 安全 / 权限 / 协议 / 跨 surface 行为
  3. 有明确测试或验证路径
  4. 不需要拆单、交人、跨 session 恢复

What it can do on your machine

Read from SKILL.md and the folder at commit 4522572. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • rg
    • bash
    • gh
    • git
    • go

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Issue Workflow Guardrail loads about 1.3k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 400 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 400 words (~1,268 tokens).

“本 skill 是当前仓库 GitHub issue 工作流的唯一生命周期 owner,负责整形、分类、计划、执行编排、独立验收(仅在需要的场景)、发布和关闭。”

— opening of SKILL.md by kxn
name
issue-workflow-guardrail

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files (scripts) in .codex/skills/issue-workflow-guardrail of kxn/codex-remote-feishu.

  • SKILL.md
  • agents/openai.yaml
  • scripts/issuectl.sh

Open the folder on GitHubat commit 4522572

Compare with similar skills

Issue Workflow Guardrail next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Issue Workflow Guardrail compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Issue Workflow Guardrail this skillkxn/codex-remote-feishu329—~1.3kAutomated safety check: PassNone
Esmfold2JimLiu/science-skills2274 repos~2.5kAutomated safety check: PassApache-2.0
Precheck PRvllm-project/vllm-omni7.1k—~1.4kAutomated safety check: PassApache-2.0
Create Simple Promptpnp/copilot-prompts892—~2.6kAutomated safety check: PassMIT
Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel1.3k—~1.1kAutomated safety check: PassCustom licence
ML Failure DebuggerLeeroo-AI/superml195—~9.5kAutomated safety check: PassApache-2.0

Similar skills

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    227 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed
  • Precheck PR

    vllm-project/vllm-omni

    Self-check your branch before creating a PR — catch dead code, prevent new model-specific Python examples, verify accuracy/perf claims, validate PR title format, and confirm merge readiness.

    7.1k GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Create Simple Prompt

    pnp/copilot-prompts

    This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…

    892 GitHub stars~2.6k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed
  • Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.

    1.3k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • ML Failure Debugger

    Leeroo-AI/superml

    Diagnoses failing ML and AI work, such as OOM, NaN, divergence, crashes, slow throughput, wrong outputs and dependency conflicts, with every claim backed by documentation citations.

    195 GitHub stars~9.5k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check passed
  • Copilot SDK

    github/awesome-copilot

    Official

    Build agentic applications with GitHub Copilot SDK. An agent skill from github/awesome-copilot.

    40k GitHub starsUsed in 4 repos~6.3k tokens
    AI & LLM EngineeringAuto-check passed

More from kxn/codex-remote-feishu

All 9 skills in this repo
  • Local Upgrade

    kxn/codex-remote-feishu

    A skill your agent uses when the user asks for this repository's local upgrade flow: 本地升级, 拉最新代码后升级本地 daemon, upgrade-local.sh, or triggering the built-in local upgrade transaction from a repo build.

    329 GitHub stars~951 tokensUpdated 8 days ago
    Auto-check passed
  • Safe Push

    kxn/codex-remote-feishu

    A skill your agent uses when pushing committed changes from this repository, especially when git push may fail because the remote branch advanced.

    329 GitHub stars~639 tokensUpdated 8 days ago
    Auto-check passed
  • Issue Doc Sync

    kxn/codex-remote-feishu

    A skill your agent uses when syncing closed GitHub issues back into repo docs.

    329 GitHub stars~932 tokensUpdated 8 days ago
    Auto-check passed
  • Relay Stack Playbook

    kxn/codex-remote-feishu

    A skill your agent uses when working on this repository's relay stack: Codex app-server protocol translation, relayd, relay-wrapper, Feishu bot integration, VS Code remote integration, or real-stack…

    329 GitHub stars~1.3k tokensUpdated 8 days ago
    Auto-check passed
  • Build Page Mock

    kxn/codex-remote-feishu

    A skill your agent uses when creating or revising a page mock, browser-runnable prototype, or interactive demo for this repository's web, setup, onboarding, status, or admin pages, and also when…

    329 GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed
  • Feishu UI State Machine Guardrail

    kxn/codex-remote-feishu

    Audit and update this repository's canonical Feishu card UI state machine after changing Feishu card state-machine logic carriers such as callback schema/parsing, card action routing, inline replace…

    329 GitHub stars~1.2k tokensUpdated 8 days ago
    Auto-check passed

Works with

Questions about Issue Workflow Guardrail

What does Issue Workflow Guardrail do?

A skill your agent uses when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots…. Issue Workflow Guardrail is an agent skill from kxn/codex-remote-feishu. Use when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots on real handoffs, product decision gates, result roll-up, and close-out.

When should I use Issue Workflow Guardrail?

Issue Workflow Guardrail fits situations like: handling a GitHub issue in this repository: raw issue shaping; implementability reassessment; fast/full classification; parent/child orchestration.

How do I install Issue Workflow Guardrail in Claude Code?

Run `npx skills add kxn/codex-remote-feishu --skill issue-workflow-guardrail -a claude-code`. Or copy the skill folder (.codex/skills/issue-workflow-guardrail in kxn/codex-remote-feishu) into .claude/skills/issue-workflow-guardrail in your project. Claude Code loads it when a task matches its description.

How do I install Issue Workflow Guardrail in Codex?

Run `npx skills add kxn/codex-remote-feishu --skill issue-workflow-guardrail -a codex`. Or copy the skill folder (.codex/skills/issue-workflow-guardrail in kxn/codex-remote-feishu) into .agents/skills/issue-workflow-guardrail in your project. Codex loads it when a task matches its description.

Can I use Issue Workflow Guardrail in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kxn/codex-remote-feishu --skill issue-workflow-guardrail -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/issue-workflow-guardrail, .gemini/skills/issue-workflow-guardrail, .github/skills/issue-workflow-guardrail and .opencode/skills/issue-workflow-guardrail in your project.

What does Issue Workflow Guardrail need to run?

Going by SKILL.md and its folder, Issue Workflow Guardrail needs a shell for the scripts in its folder and the command-line tools its instructions call (rg, bash, gh, git and go). Our summary lists: A Bash shell.

Does Issue Workflow Guardrail access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Issue Workflow Guardrail safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Issue Workflow Guardrail use?

No licence was found for Issue Workflow Guardrail or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Issue Workflow Guardrail use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Issue Workflow Guardrail?

Skills that share tags, products or a category with Issue Workflow Guardrail: Esmfold2 (JimLiu/science-skills, 227 stars), Precheck PR (vllm-project/vllm-omni, 7.1k stars), Create Simple Prompt (pnp/copilot-prompts, 892 stars) and Gptqmodel Tokenizer Normalization (ModelCloud/GPTQModel, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Issue Workflow Guardrail?

kxn (a GitHub user) maintains it in kxn/codex-remote-feishu, which has 329 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 1, 2026.

Source: kxn/codex-remote-feishu on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.